© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 80055
    Prev
    Next
    INDEX
    Explanations

    replacement or names with German/French hints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dissertation
    -0.86
     vais
    -0.85
    ented
    -0.83
     ◄
    -0.82
    ércio
    -0.80
    ffective
    -0.80
     توا
    -0.80
    endo
    -0.79
    ***************/
    -0.79
     gâ
    -0.78
    POSITIVE LOGITS
     because
    0.87
     infatu
    0.85
    POLYGON
    0.80
    cior
    0.74
    思议
    0.73
     rubrique
    0.72
    ല
    0.72
     clínicas
    0.72
     trình
    0.72
     menetap
    0.72
    Activations Density 0.080%

    No Known Activations